Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Intangible cultural heritage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    注意的是
    1.25
     Ă
    1.20
    注意
    1.16
    en
    1.15
     Ï
    1.14
     Anfang
    1.10
    তে
    1.07
    ات
    1.07
    توان
    1.06
    те
    1.05
    POSITIVE LOGITS
    م
    1.42
    डिशा
    1.19
     saur
    1.13
     shamp
    1.07
    至於
    1.05
     borrar
    1.05
    這裡是
    1.05
     веке
    1.04
    lava
    1.02
     clogging
    1.02
    Act Density 0.002%

    No Known Activations